Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4324 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4273. Min Range: -9.4273
Max Act: 9.4273. Min Act: -0.1700
Data Index: 3668970 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4273. Min Range: -9.4273
Max Act: 9.1773. Min Act: -0.1700
Data Index: 4524763 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4273. Min Range: -9.4273
Max Act: 9.1773. Min Act: -0.1700
Data Index: 2983513 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.8648. Min Act: -0.1700
Data Index: 4050424 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.8023. Min Act: -0.1700
Data Index: 6103172 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.7398. Min Act: -0.1700
Data Index: 3945800 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.8648. Min Act: -0.1700
Data Index: 5863366 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.7398. Min Act: -0.1700
Data Index: 6295636 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.7398. Min Act: -0.1700
Data Index: 2206731 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.7398. Min Act: -0.1700
Data Index: 6822953 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.7398. Min Act: -0.1700
Data Index: 8350615 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.6773. Min Act: -0.1700
Data Index: 2798418 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.6148. Min Act: -0.1700
Data Index: 5586718 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.5523. Min Act: -0.1700
Data Index: 2320245 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.5523. Min Act: -0.1700
Data Index: 1081094 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.5523. Min Act: -0.1700
Data Index: 6257135 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.5523. Min Act: -0.1700
Data Index: 5064834 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.4898. Min Act: -0.1700
Data Index: 6489736 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.4898. Min Act: -0.1700
Data Index: 4330024 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4273. Min Range: -9.4273
Max Act: 8.4898. Min Act: -0.1700
Data Index: 4596417 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19